can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 6000 Ada (48GB) run Ornith 1.5 9B?

Ornith · MIT · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Ornith 1.5 9B at FP16 · 17.9 GB · 35–53 tok/s on a NVIDIA RTX 6000 Ada (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K4.1 GB116–174 tok/sRuns great
Q3_K_M4.9 GB101–152 tok/sRuns great
Q4_K_M5.9 GB89–133 tok/sRuns great
Q5_K_M6.9 GB80–119 tok/sRuns great
Q6_K7.7 GB73–109 tok/sRuns great
Q8_09.6 GB61–92 tok/sRuns great
FP1617.9 GB35–53 tok/sRuns great

Ran Ornith 1.5 9B on a NVIDIA RTX 6000 Ada (48GB)? Add your real numbers →